diff options
author | Felix Cheung <felixcheung_m@hotmail.com> | 2016-10-30 16:21:37 -0700 |
---|---|---|
committer | Felix Cheung <felixcheung@apache.org> | 2016-10-30 16:21:37 -0700 |
commit | 7c3786929205b962b430cf7fc292602c2993c193 (patch) | |
tree | 5805b48f8f027a92f9dd3e99aca042eee99b4cef /python/pyspark/ml/classification.py | |
parent | b6879b8b3518c71c23262554fcb0fdad60287011 (diff) | |
download | spark-7c3786929205b962b430cf7fc292602c2993c193.tar.gz spark-7c3786929205b962b430cf7fc292602c2993c193.tar.bz2 spark-7c3786929205b962b430cf7fc292602c2993c193.zip |
[SPARK-18110][PYTHON][ML] add missing parameter in Python for RandomForest regression and classification
## What changes were proposed in this pull request?
Add subsmaplingRate to randomForestClassifier
Add varianceCol to randomForestRegressor
In Python
## How was this patch tested?
manual tests
Author: Felix Cheung <felixcheung_m@hotmail.com>
Closes #15638 from felixcheung/pyrandomforest.
Diffstat (limited to 'python/pyspark/ml/classification.py')
-rw-r--r-- | python/pyspark/ml/classification.py | 11 |
1 files changed, 6 insertions, 5 deletions
diff --git a/python/pyspark/ml/classification.py b/python/pyspark/ml/classification.py index 3f763a10d4..d9ff356b94 100644 --- a/python/pyspark/ml/classification.py +++ b/python/pyspark/ml/classification.py @@ -758,20 +758,21 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred probabilityCol="probability", rawPredictionCol="rawPrediction", maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini", - numTrees=20, featureSubsetStrategy="auto", seed=None): + numTrees=20, featureSubsetStrategy="auto", seed=None, subsamplingRate=1.0): """ __init__(self, featuresCol="features", labelCol="label", predictionCol="prediction", \ probabilityCol="probability", rawPredictionCol="rawPrediction", \ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, impurity="gini", \ - numTrees=20, featureSubsetStrategy="auto", seed=None) + numTrees=20, featureSubsetStrategy="auto", seed=None, subsamplingRate=1.0) """ super(RandomForestClassifier, self).__init__() self._java_obj = self._new_java_obj( "org.apache.spark.ml.classification.RandomForestClassifier", self.uid) self._setDefault(maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, - impurity="gini", numTrees=20, featureSubsetStrategy="auto") + impurity="gini", numTrees=20, featureSubsetStrategy="auto", + subsamplingRate=1.0) kwargs = self.__init__._input_kwargs self.setParams(**kwargs) @@ -781,13 +782,13 @@ class RandomForestClassifier(JavaEstimator, HasFeaturesCol, HasLabelCol, HasPred probabilityCol="probability", rawPredictionCol="rawPrediction", maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=None, - impurity="gini", numTrees=20, featureSubsetStrategy="auto"): + impurity="gini", numTrees=20, featureSubsetStrategy="auto", subsamplingRate=1.0): """ setParams(self, featuresCol="features", labelCol="label", predictionCol="prediction", \ probabilityCol="probability", rawPredictionCol="rawPrediction", \ maxDepth=5, maxBins=32, minInstancesPerNode=1, minInfoGain=0.0, \ maxMemoryInMB=256, cacheNodeIds=False, checkpointInterval=10, seed=None, \ - impurity="gini", numTrees=20, featureSubsetStrategy="auto") + impurity="gini", numTrees=20, featureSubsetStrategy="auto", subsamplingRate=1.0) Sets params for linear classification. """ kwargs = self.setParams._input_kwargs |